Anurag Sharma's Projects
scraping google adwords ads
Example notebooks that show how to apply machine learning, deep learning and reinforcement learning in Amazon SageMaker
Dash š with animated scatter map on mapbox/plotly (COVID data) for tracking day to day evolution of COVID-19 through the world.
This includes dimensionality reduction techniques like PCA & SVD.
Problem Statement: To predict whether a given mail will get a reply or not. Given Dataset: A text file with emails and their metadata in hierarchy To predict: Reply/ No reply Our Approach: Load Data Extracting Data: Extracting text email subject and body data from the text file Text Data Cleaning and Preprocessing Feature engineering : extracting additional features from emails (such as header subject length, email body lengths, recepient count, attachment count) Modelling: 5.1 BERT Embeddings from the text data 5.2 combine with other features 5.3 train test split 5.4 predict using MLP classifier 5.5 check F-1 score and plot ROC
My first repository
AnalyticsVidhya HR analytics problem
Movie recommendation with NNMF and various optimization techniques like Regularized GD, Sliding window GD, Line Search GD, PSO.
Implement Multivarite Time Series models like VAR, GARCH and test like Granger causality test for time series forecasting.
Code Demonstrating Phase Chnages in RandomGraphs
Includes code of PageRank algorithm and Modified Version of PageRank Algorithm
Regression Techniques like Linear Regression, Logistic Regression, Lasso , Ridge implemented from scratch
Sentiment Analysis on Amazon phone reviews dataset
Code done as part of my course-work.
Scraping google ads which appear on google search using selenium.